ChineseResearchLaTeX is a collection of LaTeX templates and an AI-assisted workflow for preparing Chinese research documents such as grant proposals, papers, theses, and academic CVs. Researchers use it to plan, format, review, compile, and revise these documents with human oversight. The catalogue skills and instructions support its agent-based research-writing workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add huangwb8/ChineseResearchLaTeX --skill nsfc-justification-writergit clone --depth 1 https://github.com/huangwb8/ChineseResearchLaTeXWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/huangwb8/chineseresearchlatex/nsfc-justification-writer)<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/nsfc-justification-writer"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/nsfc-justification-writer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/nsfc-justification-writer"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/nsfc-justification-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00110 | $0.02163 |
| Opus 5 | $0.00055 | $0.01081 |
| Sonnet 5 | $0.00022 | $0.00433 |
| Haiku 4.5 | $0.00011 | $0.00216 |
Grade A, and why
nsfc-justification-writer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
科研立项依据写作器
流程
输入
按用户请求和配置文件提供必要输入；缺失信息应明确列出并停止依赖该输入的步骤。
执行步骤
- 本 skill 设计缺陷导致 bug 时，按
bensz-collect-bugs记录到~/.bensz-skills/bugs/，不要改用户本地已安装 skill；可用 workaround 时先记录再继续。 - 仅用户明确要求公开上报时，才用本地
gh通过该 skill 上传新增 bug 到huangwb8/bensz-bugs；不 pull/clone 整仓库。
- 先写领域价值/必要性与已有证据，再将瓶颈转成待解释的关系、机制、性质或边界。
- 科学问题用疑问句追问认知缺口；假设用可证伪陈述句预测结果。研究目标、路线、验证终点不冒充问题/假设。
- 假设前以事实、文献和缺口为主；干预、比较、终点、路线放在假设后。外部文献的方法描述可作证据，不等于本项目方案前置。
- 切入点/贡献无需固定标题或段数；理论、混合、工程导向只改变措辞与证据重心，不是通过门槛。
- 逻辑与引用检查后必须读取
references/tier2_semantic_review.md，由当前宿主 AI 直接执行 Tier2 语义检查。由宿主 AI 自主规划术语、论证维度和可读性，输出“位置/障碍/影响/保真改法”。检查长句层级、指代、缩写/新概念、抽象名词、衔接和无效修饰；不科普化或因必要限定强改。 - 可读性改写须保留已核验事实、对象、限定、问题/假设、引用、标签和 LaTeX 结构；无法保真保留原句并记录风险，不补事实/证据。
措辞边界：吹牛式、绝对化或无依据夸大由宿主 AI 按 references/boastful_expression_guidelines.md 语义复核并归入逻辑/表达建议；Python 只做路径、结构命令、引用 key 等确定性检查，不用固定词表判定。
- 读取目标文件和上下文；目标缺失时自动追踪
main.tex，按确定性优先级选择候选，必要时创建白名单内的默认正文文件。 - 检查问题—假设—证据—研究内容闭环及引用 key；随后必做 Tier2，结果分为“事实问题、逻辑问题、表达建议”。
- 完成检查后自动复核专业可读性；
polish先在内部锁定事实/逻辑/引用，再做受约束精修，不向用户提问。 - 自动生成完整正文或 unified diff；发现结构命令变化时自动回退为正文-only 提案并重试。
- 通过白名单、引用和质量检查后自动写入；写入前备份，写入后展示 diff、假设与回滚入口。
- 字数与引用检查可独立运行；流程不绑定固定标题或维度清单。
scripts/run.py preview：自动生成 diff 并按guardrails.output_mode写入；需要只读检查时显式加--dry-run。refs、wordcount：独立引用/字数工具；术语、论证维度和可读性由 Tier2 宿主 AI 规划。diagnose：仅执行 Tier1 确定性诊断，并提示宿主 AI 读取references/tier2_semantic_review.md；不主动调用模型、不生成 Tier2 fallback 结论。coach、review：主流程必须包含由宿主 AI 直接执行的 Tier2 语义检查。吹牛式/绝对化风险按参考准则由 AI 判断，脚本不做固定短语命中。apply-section：legacy 标题替换写入；新流程优先使用完整正文提案自动写入，不依赖\\subsubsection。diff、rollback：查看或回滚自动写入变更；回滚命令仍需显式--yes以避免误操作。
按任务先阅读 references/tier2_semantic_review.md，再按其中需要阅读 references/scientific_question_guidelines.md、references/scientific_hypothesis_guidelines.md、references/professional_readability_guidelines.md 和 references/boastful_expression_guidelines.md。用户流程、脚本用法和架构边界见 README.md；检查维度由宿主 AI 自主规划，不依赖固定术语矩阵或四维度门槛。
输出
默认输出：
目标文件（自动选择及依据）：...
修改范围：仅白名单正文
主要问题：...
建议正文或 unified diff：...
引用与事实守护：...
未修改：标题、结构命令、配置和样式文件
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/examples/biology/example_001.metadata.yaml 297 B
- assets/examples/biology/example_001.tex 925 B
- assets/examples/chemistry/example_001.metadata.yaml 296 B
- assets/examples/chemistry/example_001.tex 842 B
- assets/examples/cs/example_001.metadata.yaml 314 B
- assets/examples/cs/example_001.tex 1.5 KB
- assets/examples/engineering/example_001.metadata.yaml 300 B
- assets/examples/engineering/example_001.tex 704 B
- assets/examples/materials/example_001.metadata.yaml 310 B
- assets/examples/materials/example_001.tex 1.6 KB
- assets/examples/math/example_001.metadata.yaml 294 B
- assets/examples/math/example_001.tex 912 B
- assets/examples/medical/example_001.metadata.yaml 299 B
- assets/examples/medical/example_001.tex 722 B
- assets/examples/README.md 992 B
- assets/prompts/review_suggestions.txt 1.6 KB
- assets/prompts/writing_coach.txt 2.7 KB
- assets/README.md 877 B
- assets/templates/html/report_template.html 7.3 KB
- assets/templates/phrase_patterns.md 1.5 KB
- assets/templates/structure_template.tex 881 B
- CHANGELOG.md 4.2 KB
- config.yaml 2.6 KB
- README.md 9.7 KB
- references/boastful_expression_guidelines.md 1.4 KB
- references/diagnostic_examples.md 886 B
- references/dod_checklist.md 1.5 KB
- references/info_form.md 2.1 KB
- references/methodology_term_examples.md 1.1 KB
- references/professional_readability_guidelines.md 1.2 KB
- references/scientific_hypothesis_guidelines.md 1.5 KB
- references/scientific_question_guidelines.md 1.2 KB
- references/theoretical_innovation_guidelines.md 1.8 KB
- references/theoretical_innovation_plan.md 692 B
- references/tier2_semantic_review.md 2.3 KB
- scripts/core/__init__.py 1.3 KB runs code
- scripts/core/ai_integration.py 6.7 KB runs code
- scripts/core/bib_manager_integration.py 3.1 KB runs code
- scripts/core/change_guard.py 1.5 KB runs code
- scripts/core/config_access.py 1.3 KB runs code
- scripts/core/config_loader.py 19 KB runs code
- scripts/core/constraints.py 6.4 KB runs code
- scripts/core/diagnostic.py 7.7 KB runs code
- scripts/core/editor.py 2.2 KB runs code
- scripts/core/errors.py 4.1 KB runs code
- scripts/core/example_matcher.py 10 KB runs code
- scripts/core/hard_rules.py 1.2 KB runs code
- scripts/core/html_report.py 6.3 KB runs code
- scripts/core/hybrid_coordinator.py 12 KB runs code
- scripts/core/info_form.py 5.0 KB runs code
- scripts/core/io_utils.py 3.0 KB runs code
- scripts/core/latex_parser.py 11 KB runs code
- scripts/core/limits.py 1.1 KB runs code
- scripts/core/logging_utils.py 602 B runs code
- scripts/core/observability.py 1.4 KB runs code
- scripts/core/prompt_templates.py 2.8 KB runs code
- scripts/core/quality_gate.py 771 B runs code
- scripts/core/reference_validator.py 5.8 KB runs code
- scripts/core/review_advice.py 6.9 KB runs code
- scripts/core/review_integration.py 8.0 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · +2 lines 24a5a5f72796
- 12d ago First seen · 94 lines · 110 tokens per session scan A 1ff10162abdc
nsfc-justification-writer is a skill published in the GitHub repository huangwb8/ChineseResearchLaTeX (2,721 stars, last pushed 3d ago), licensed MIT. It adds 110 tokens to every session and 2,163 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…
git-commit
A Git assistant for reviewing local changes and creating conventional commit messages, which are standardized summaries of code changes. It can also run Git hooks and push the commit.